Ensemble-based deep learning for estimating PM2.5 over California with multisource big data including wildfire smoke
•California has high variability in PM2.5 sources, meteorology and topography.•We used ensemble deep learning with multisource big data to improve PM2.5 estimates.•We reliably imputed missing satellite AOD and fused wildfire dispersion estimates.•Our model achieved high PM2.5 prediction performance...
Saved in:
| Published in: | Environment international Vol. 145; p. 106143 |
|---|---|
| Main Authors: | , , , , , , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Goddard Space Flight Center
Elsevier Ltd
01.12.2020
Elsevier |
| Subjects: | |
| ISSN: | 0160-4120, 1873-6750, 1873-6750 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | •California has high variability in PM2.5 sources, meteorology and topography.•We used ensemble deep learning with multisource big data to improve PM2.5 estimates.•We reliably imputed missing satellite AOD and fused wildfire dispersion estimates.•Our model achieved high PM2.5 prediction performance with uncertainty estimates.
Estimating PM2.5 concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies. This is particularly challenging for California, which has high variability in natural (e.g, wildfires, dust) and anthropogenic emissions, meteorology, topography (e.g. desert surfaces, mountains, snow cover) and land use.
Using ensemble-based deep learning with big data fused from multiple sources we developed a PM2.5 prediction model with uncertainty estimates at a high spatial (1 km × 1 km) and temporal (weekly) resolution for a 10-year time span (2008–2017). We leveraged autoencoder-based full residual deep networks to model complex nonlinear interrelationships among PM2.5 emission, transport and dispersion factors and other influential features. These included remote sensing data (MAIAC aerosol optical depth (AOD), normalized difference vegetation index, impervious surface), MERRA-2 GMI Replay Simulation (M2GMI) output, wildfire smoke plume dispersion, meteorology, land cover, traffic, elevation, and spatiotemporal trends (geo-coordinates, temporal basis functions, time index). As one of the primary predictors of interest with substantial missing data in California related to bright surfaces, cloud cover and other known interferences, missing MAIAC AOD observations were imputed and adjusted for relative humidity and vertical distribution. Wildfire smoke contribution to PM2.5 was also calculated through HYSPLIT dispersion modeling of smoke emissions derived from MODIS fire radiative power using the Fire Energetics and Emissions Research version 1.0 model.
Ensemble deep learning to predict PM2.5 achieved an overall mean training RMSE of 1.54 μg/m3 (R2: 0.94) and test RMSE of 2.29 μg/m3 (R2: 0.87). The top predictors included M2GMI carbon monoxide mixing ratio in the bottom layer, temporal basis functions, spatial location, air temperature, MAIAC AOD, and PM2.5 sea salt mass concentration. In an independent test using three long-term AQS sites and one short-term non-AQS site, our model achieved a high correlation (>0.8) and a low RMSE (<3 μg/m3). Statewide predictions indicated that our model can capture the spatial distribution and temporal peaks in wildfire-related PM2.5. The coefficient of variation indicated highest uncertainty over deciduous and mixed forests and open water land covers.
Our method can be generalized to other regions, including those having a mix of major urban areas, deserts, intensive smoke events, snow cover and complex terrains, where PM2.5 has previously been challenging to predict. Prediction uncertainty estimates can also inform further model development and measurement error evaluations in exposure and health studies. |
|---|---|
| AbstractList | •California has high variability in PM2.5 sources, meteorology and topography.•We used ensemble deep learning with multisource big data to improve PM2.5 estimates.•We reliably imputed missing satellite AOD and fused wildfire dispersion estimates.•Our model achieved high PM2.5 prediction performance with uncertainty estimates.
Estimating PM2.5 concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies. This is particularly challenging for California, which has high variability in natural (e.g, wildfires, dust) and anthropogenic emissions, meteorology, topography (e.g. desert surfaces, mountains, snow cover) and land use.
Using ensemble-based deep learning with big data fused from multiple sources we developed a PM2.5 prediction model with uncertainty estimates at a high spatial (1 km × 1 km) and temporal (weekly) resolution for a 10-year time span (2008–2017). We leveraged autoencoder-based full residual deep networks to model complex nonlinear interrelationships among PM2.5 emission, transport and dispersion factors and other influential features. These included remote sensing data (MAIAC aerosol optical depth (AOD), normalized difference vegetation index, impervious surface), MERRA-2 GMI Replay Simulation (M2GMI) output, wildfire smoke plume dispersion, meteorology, land cover, traffic, elevation, and spatiotemporal trends (geo-coordinates, temporal basis functions, time index). As one of the primary predictors of interest with substantial missing data in California related to bright surfaces, cloud cover and other known interferences, missing MAIAC AOD observations were imputed and adjusted for relative humidity and vertical distribution. Wildfire smoke contribution to PM2.5 was also calculated through HYSPLIT dispersion modeling of smoke emissions derived from MODIS fire radiative power using the Fire Energetics and Emissions Research version 1.0 model.
Ensemble deep learning to predict PM2.5 achieved an overall mean training RMSE of 1.54 μg/m3 (R2: 0.94) and test RMSE of 2.29 μg/m3 (R2: 0.87). The top predictors included M2GMI carbon monoxide mixing ratio in the bottom layer, temporal basis functions, spatial location, air temperature, MAIAC AOD, and PM2.5 sea salt mass concentration. In an independent test using three long-term AQS sites and one short-term non-AQS site, our model achieved a high correlation (>0.8) and a low RMSE (<3 μg/m3). Statewide predictions indicated that our model can capture the spatial distribution and temporal peaks in wildfire-related PM2.5. The coefficient of variation indicated highest uncertainty over deciduous and mixed forests and open water land covers.
Our method can be generalized to other regions, including those having a mix of major urban areas, deserts, intensive smoke events, snow cover and complex terrains, where PM2.5 has previously been challenging to predict. Prediction uncertainty estimates can also inform further model development and measurement error evaluations in exposure and health studies. Estimating PM2.5 concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies. This is particularly challenging for California, which has high variability in natural (e.g. wildfires, dust) and anthropogenic emissions, meteorology, topography (e.g. desert surfaces, mountains, snow cover) and land use. Estimating PM₂.₅ concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies. This is particularly challenging for California, which has high variability in natural (e.g, wildfires, dust) and anthropogenic emissions, meteorology, topography (e.g. desert surfaces, mountains, snow cover) and land use.Using ensemble-based deep learning with big data fused from multiple sources we developed a PM₂.₅ prediction model with uncertainty estimates at a high spatial (1 km × 1 km) and temporal (weekly) resolution for a 10-year time span (2008–2017). We leveraged autoencoder-based full residual deep networks to model complex nonlinear interrelationships among PM₂.₅ emission, transport and dispersion factors and other influential features. These included remote sensing data (MAIAC aerosol optical depth (AOD), normalized difference vegetation index, impervious surface), MERRA-2 GMI Replay Simulation (M2GMI) output, wildfire smoke plume dispersion, meteorology, land cover, traffic, elevation, and spatiotemporal trends (geo-coordinates, temporal basis functions, time index). As one of the primary predictors of interest with substantial missing data in California related to bright surfaces, cloud cover and other known interferences, missing MAIAC AOD observations were imputed and adjusted for relative humidity and vertical distribution. Wildfire smoke contribution to PM₂.₅ was also calculated through HYSPLIT dispersion modeling of smoke emissions derived from MODIS fire radiative power using the Fire Energetics and Emissions Research version 1.0 model.Ensemble deep learning to predict PM₂.₅ achieved an overall mean training RMSE of 1.54 μg/m³ (R²: 0.94) and test RMSE of 2.29 μg/m³ (R²: 0.87). The top predictors included M2GMI carbon monoxide mixing ratio in the bottom layer, temporal basis functions, spatial location, air temperature, MAIAC AOD, and PM₂.₅ sea salt mass concentration. In an independent test using three long-term AQS sites and one short-term non-AQS site, our model achieved a high correlation (>0.8) and a low RMSE (<3 μg/m³). Statewide predictions indicated that our model can capture the spatial distribution and temporal peaks in wildfire-related PM₂.₅. The coefficient of variation indicated highest uncertainty over deciduous and mixed forests and open water land covers.Our method can be generalized to other regions, including those having a mix of major urban areas, deserts, intensive smoke events, snow cover and complex terrains, where PM₂.₅ has previously been challenging to predict. Prediction uncertainty estimates can also inform further model development and measurement error evaluations in exposure and health studies. Introduction: Estimating PM2.5 concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies. This is particularly challenging for California, which has high variability in natural (e.g, wildfires, dust) and anthropogenic emissions, meteorology, topography (e.g. desert surfaces, mountains, snow cover) and land use. Methods: Using ensemble-based deep learning with big data fused from multiple sources we developed a PM2.5 prediction model with uncertainty estimates at a high spatial (1 km × 1 km) and temporal (weekly) resolution for a 10-year time span (2008–2017). We leveraged autoencoder-based full residual deep networks to model complex nonlinear interrelationships among PM2.5 emission, transport and dispersion factors and other influential features. These included remote sensing data (MAIAC aerosol optical depth (AOD), normalized difference vegetation index, impervious surface), MERRA-2 GMI Replay Simulation (M2GMI) output, wildfire smoke plume dispersion, meteorology, land cover, traffic, elevation, and spatiotemporal trends (geo-coordinates, temporal basis functions, time index). As one of the primary predictors of interest with substantial missing data in California related to bright surfaces, cloud cover and other known interferences, missing MAIAC AOD observations were imputed and adjusted for relative humidity and vertical distribution. Wildfire smoke contribution to PM2.5 was also calculated through HYSPLIT dispersion modeling of smoke emissions derived from MODIS fire radiative power using the Fire Energetics and Emissions Research version 1.0 model. Results: Ensemble deep learning to predict PM2.5 achieved an overall mean training RMSE of 1.54 μg/m3 (R2: 0.94) and test RMSE of 2.29 μg/m3 (R2: 0.87). The top predictors included M2GMI carbon monoxide mixing ratio in the bottom layer, temporal basis functions, spatial location, air temperature, MAIAC AOD, and PM2.5 sea salt mass concentration. In an independent test using three long-term AQS sites and one short-term non-AQS site, our model achieved a high correlation (>0.8) and a low RMSE (<3 μg/m3). Statewide predictions indicated that our model can capture the spatial distribution and temporal peaks in wildfire-related PM2.5. The coefficient of variation indicated highest uncertainty over deciduous and mixed forests and open water land covers. Conclusion: Our method can be generalized to other regions, including those having a mix of major urban areas, deserts, intensive smoke events, snow cover and complex terrains, where PM2.5 has previously been challenging to predict. Prediction uncertainty estimates can also inform further model development and measurement error evaluations in exposure and health studies. Estimating PM2.5 concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies. This is particularly challenging for California, which has high variability in natural (e.g, wildfires, dust) and anthropogenic emissions, meteorology, topography (e.g. desert surfaces, mountains, snow cover) and land use.INTRODUCTIONEstimating PM2.5 concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies. This is particularly challenging for California, which has high variability in natural (e.g, wildfires, dust) and anthropogenic emissions, meteorology, topography (e.g. desert surfaces, mountains, snow cover) and land use.Using ensemble-based deep learning with big data fused from multiple sources we developed a PM2.5 prediction model with uncertainty estimates at a high spatial (1 km × 1 km) and temporal (weekly) resolution for a 10-year time span (2008-2017). We leveraged autoencoder-based full residual deep networks to model complex nonlinear interrelationships among PM2.5 emission, transport and dispersion factors and other influential features. These included remote sensing data (MAIAC aerosol optical depth (AOD), normalized difference vegetation index, impervious surface), MERRA-2 GMI Replay Simulation (M2GMI) output, wildfire smoke plume dispersion, meteorology, land cover, traffic, elevation, and spatiotemporal trends (geo-coordinates, temporal basis functions, time index). As one of the primary predictors of interest with substantial missing data in California related to bright surfaces, cloud cover and other known interferences, missing MAIAC AOD observations were imputed and adjusted for relative humidity and vertical distribution. Wildfire smoke contribution to PM2.5 was also calculated through HYSPLIT dispersion modeling of smoke emissions derived from MODIS fire radiative power using the Fire Energetics and Emissions Research version 1.0 model.METHODSUsing ensemble-based deep learning with big data fused from multiple sources we developed a PM2.5 prediction model with uncertainty estimates at a high spatial (1 km × 1 km) and temporal (weekly) resolution for a 10-year time span (2008-2017). We leveraged autoencoder-based full residual deep networks to model complex nonlinear interrelationships among PM2.5 emission, transport and dispersion factors and other influential features. These included remote sensing data (MAIAC aerosol optical depth (AOD), normalized difference vegetation index, impervious surface), MERRA-2 GMI Replay Simulation (M2GMI) output, wildfire smoke plume dispersion, meteorology, land cover, traffic, elevation, and spatiotemporal trends (geo-coordinates, temporal basis functions, time index). As one of the primary predictors of interest with substantial missing data in California related to bright surfaces, cloud cover and other known interferences, missing MAIAC AOD observations were imputed and adjusted for relative humidity and vertical distribution. Wildfire smoke contribution to PM2.5 was also calculated through HYSPLIT dispersion modeling of smoke emissions derived from MODIS fire radiative power using the Fire Energetics and Emissions Research version 1.0 model.Ensemble deep learning to predict PM2.5 achieved an overall mean training RMSE of 1.54 μg/m3 (R2: 0.94) and test RMSE of 2.29 μg/m3 (R2: 0.87). The top predictors included M2GMI carbon monoxide mixing ratio in the bottom layer, temporal basis functions, spatial location, air temperature, MAIAC AOD, and PM2.5 sea salt mass concentration. In an independent test using three long-term AQS sites and one short-term non-AQS site, our model achieved a high correlation (>0.8) and a low RMSE (<3 μg/m3). Statewide predictions indicated that our model can capture the spatial distribution and temporal peaks in wildfire-related PM2.5. The coefficient of variation indicated highest uncertainty over deciduous and mixed forests and open water land covers.RESULTSEnsemble deep learning to predict PM2.5 achieved an overall mean training RMSE of 1.54 μg/m3 (R2: 0.94) and test RMSE of 2.29 μg/m3 (R2: 0.87). The top predictors included M2GMI carbon monoxide mixing ratio in the bottom layer, temporal basis functions, spatial location, air temperature, MAIAC AOD, and PM2.5 sea salt mass concentration. In an independent test using three long-term AQS sites and one short-term non-AQS site, our model achieved a high correlation (>0.8) and a low RMSE (<3 μg/m3). Statewide predictions indicated that our model can capture the spatial distribution and temporal peaks in wildfire-related PM2.5. The coefficient of variation indicated highest uncertainty over deciduous and mixed forests and open water land covers.Our method can be generalized to other regions, including those having a mix of major urban areas, deserts, intensive smoke events, snow cover and complex terrains, where PM2.5 has previously been challenging to predict. Prediction uncertainty estimates can also inform further model development and measurement error evaluations in exposure and health studies.CONCLUSIONOur method can be generalized to other regions, including those having a mix of major urban areas, deserts, intensive smoke events, snow cover and complex terrains, where PM2.5 has previously been challenging to predict. Prediction uncertainty estimates can also inform further model development and measurement error evaluations in exposure and health studies. |
| ArticleNumber | 106143 |
| Audience | PUBLIC |
| Author | Wu, Jun Franklin, Meredith Pavlovic, Nathan McClure, Crystal Breton, Carrie Girguis, Mariam Habre, Rima Li, Lianfa Oman, Luke D. Lurmann, Frederick Gilliland, Frank |
| AuthorAffiliation | 1. Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA 2. State Key Laboratory of Resources and Environmental Information System, Institute of Geographical Sciences and Natural Resources, Chinese Academy of Sciences, Beijing, China 3. Sonoma Technology, Inc., Petaluma, CA, USA 5. Goddard Space Flight Center, National Aeronautics and Space Administration, Greenbelt, MD, USA 4. Program in Public Health, Susan and Henry Samueli College of Health Sciences, University of California, Irvine, CA, USA |
| AuthorAffiliation_xml | – name: 3. Sonoma Technology, Inc., Petaluma, CA, USA – name: 1. Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA – name: 5. Goddard Space Flight Center, National Aeronautics and Space Administration, Greenbelt, MD, USA – name: 2. State Key Laboratory of Resources and Environmental Information System, Institute of Geographical Sciences and Natural Resources, Chinese Academy of Sciences, Beijing, China – name: 4. Program in Public Health, Susan and Henry Samueli College of Health Sciences, University of California, Irvine, CA, USA |
| Author_xml | – sequence: 1 givenname: Lianfa surname: Li fullname: Li, Lianfa email: lianfali@usc.edu organization: Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA – sequence: 2 givenname: Mariam surname: Girguis fullname: Girguis, Mariam organization: Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA – sequence: 3 givenname: Frederick surname: Lurmann fullname: Lurmann, Frederick organization: Sonoma Technology, Inc., Petaluma, CA, USA – sequence: 4 givenname: Nathan orcidid: 0000-0003-2127-3940 surname: Pavlovic fullname: Pavlovic, Nathan organization: Sonoma Technology, Inc., Petaluma, CA, USA – sequence: 5 givenname: Crystal orcidid: 0000-0001-7477-5528 surname: McClure fullname: McClure, Crystal organization: Sonoma Technology, Inc., Petaluma, CA, USA – sequence: 6 givenname: Meredith surname: Franklin fullname: Franklin, Meredith organization: Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA – sequence: 7 givenname: Jun orcidid: 0000-0002-2693-7112 surname: Wu fullname: Wu, Jun organization: Program in Public Health, Susan and Henry Samueli College of Health Sciences, University of California, Irvine, CA, USA – sequence: 8 givenname: Luke D. orcidid: 0000-0002-5487-2598 surname: Oman fullname: Oman, Luke D. organization: Goddard Space Flight Center, National Aeronautics and Space Administration, Greenbelt, MD, USA – sequence: 9 givenname: Carrie surname: Breton fullname: Breton, Carrie organization: Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA – sequence: 10 givenname: Frank surname: Gilliland fullname: Gilliland, Frank organization: Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA – sequence: 11 givenname: Rima orcidid: 0000-0003-2103-1706 surname: Habre fullname: Habre, Rima email: habre@usc.edu organization: Department of Preventive Medicine, University of Southern California, Los Angeles, CA, USA |
| BookMark | eNqFUk1v1DAQjVAR3Rb-QQ85csni7yQckFBVoFIRHOBsOfZk68WxF9vZqv8e72aFVA70ZHnevKc3M--iOvPBQ1VdYbTGCIt32zX4vfV5TRA5lARm9EW1wl1LG9FydFatShtqGCbovLpIaYsQIqzjr6pzSvoOtVSsqnzjE0yDg2ZQCUxtAHa1AxW99Zt6DLGGlO2k8uH7_StZ8zrsIdbXytmCeqvqB5vv62l22aYwRw31YDe1UVnV1ms3mwPzwToz2gh1msIveF29HJVL8Ob0XlY_P938uP7S3H37fHv98a7RXKDcKIGBDwYoEUKrVlOkOsx51zJOFO2YIoZhjHQPQvCeMqw5YSNniKJ2xILRy-p20TVBbeUuljniowzKymMhxI1UMVvtQGI09JgahYdBsIFSpXtlaNupoeU9I7pofVi0dvMwgdHgc1TuiehTxNt7uQl72RYjHSZF4O1JIIbfc9mqnGzS4JzyEOYkCecEYdyVSZ5tZUz0xRXrSitbWnUMKUUY_zrCSB5yIrdyyYk85EQuOSm09__QtM3lyOHg3brnyFcL2aukZGGkI8wR6sQRPm0Kymn3FqJM2oLXYEoAdC67t__X_wPjF-Rz |
| CitedBy_id | crossref_primary_10_1016_j_scitotenv_2022_154103 crossref_primary_10_1016_j_scs_2023_104653 crossref_primary_10_1016_j_scitotenv_2024_171122 crossref_primary_10_3390_rs15174246 crossref_primary_10_1109_TGRS_2023_3317905 crossref_primary_10_1007_s11356_021_17442_1 crossref_primary_10_1016_j_uclim_2025_102566 crossref_primary_10_1016_j_envint_2022_107719 crossref_primary_10_1016_j_envpol_2022_119347 crossref_primary_10_3390_atmos13010071 crossref_primary_10_1016_j_rse_2022_112890 crossref_primary_10_1016_j_envpol_2025_125937 crossref_primary_10_1007_s00521_024_09637_7 crossref_primary_10_1007_s40808_025_02365_4 crossref_primary_10_1029_2022EF003468 crossref_primary_10_1016_j_jhydrol_2024_131949 crossref_primary_10_1016_j_scitotenv_2024_178206 crossref_primary_10_1016_j_jclepro_2025_144813 crossref_primary_10_3390_su15032609 crossref_primary_10_1146_annurev_biodatasci_110920_093120 crossref_primary_10_1111_all_15667 crossref_primary_10_1016_j_ufug_2025_128693 crossref_primary_10_1038_s41598_025_05332_2 crossref_primary_10_1080_02626667_2023_2248112 crossref_primary_10_1016_j_atmosenv_2023_119993 crossref_primary_10_3390_atmos13020255 crossref_primary_10_3389_fenvs_2023_1223160 crossref_primary_10_1016_j_isprsjprs_2025_04_019 crossref_primary_10_3390_rs13214341 crossref_primary_10_3390_atmos14020231 crossref_primary_10_1111_ppe_12838 crossref_primary_10_1038_s41598_025_88086_1 crossref_primary_10_1016_j_scitotenv_2022_160446 crossref_primary_10_3390_rs13183790 crossref_primary_10_1016_j_isprsjprs_2021_12_002 crossref_primary_10_1016_j_spasta_2021_100533 crossref_primary_10_1038_s41598_023_29845_w crossref_primary_10_1016_j_jclepro_2022_134656 crossref_primary_10_1007_s40808_023_01831_1 crossref_primary_10_1016_j_apr_2025_102406 crossref_primary_10_3390_atmos15121469 crossref_primary_10_1016_j_scitotenv_2022_159548 crossref_primary_10_3390_rs14143392 crossref_primary_10_1088_2632_2153_adb67a crossref_primary_10_1016_j_envint_2022_107373 crossref_primary_10_1021_acs_est_4c10194 crossref_primary_10_1016_j_envint_2024_108421 crossref_primary_10_1016_j_envint_2022_107691 crossref_primary_10_1016_j_atmosenv_2024_120374 crossref_primary_10_1038_s41370_022_00470_5 crossref_primary_10_1016_j_atmosenv_2024_120531 crossref_primary_10_1016_j_eti_2023_103272 crossref_primary_10_1109_TGRS_2021_3074569 crossref_primary_10_3390_s23218863 crossref_primary_10_1016_j_jclepro_2025_146384 crossref_primary_10_1016_j_apr_2021_101110 crossref_primary_10_3390_math8122178 crossref_primary_10_3390_rs15204973 crossref_primary_10_1071_WF22048 crossref_primary_10_59978_ar03020008 |
| Cites_doi | 10.5194/acp-12-9679-2012 10.1016/j.atmosenv.2013.10.063 10.1016/j.atmosenv.2018.11.028 10.1021/acs.est.5b03709 10.1016/j.atmosenv.2006.04.044 10.1016/j.atmosenv.2014.11.066 10.1038/s41370-017-0013-x 10.1371/annotation/21f6b02b-e533-46ca-9356-86a0eef8434e 10.1111/j.1467-9868.2005.00527.x 10.1007/s11869-020-00826-6 10.3390/atmos7100129 10.1289/ehp.1409277 10.5194/acp-18-15921-2018 10.1289/ehp.1104447 10.1016/j.atmosenv.2015.02.030 10.1021/acs.est.6b01438 10.1097/HJH.0000000000000342 10.1016/j.scitotenv.2015.09.133 10.1289/ehp.0800123 10.1016/j.envint.2018.12.025 10.1029/2005JD006996 10.1016/j.rse.2009.08.009 10.1021/es400039u 10.1016/j.atmosenv.2016.11.066 10.5194/acp-14-6049-2014 10.1016/j.jenvman.2011.03.015 10.1016/j.rse.2017.06.001 10.3109/10408444.2013.861796 10.1016/j.envres.2014.06.029 10.1016/j.atmosenv.2018.03.017 10.1016/j.atmosenv.2010.06.060 10.1016/S1352-2310(00)00330-7 10.1002/2014GL059576 10.1080/09603123.2016.1217315 10.1016/j.apr.2016.12.014 10.1016/j.rse.2013.08.032 10.5194/acp-14-6643-2014 10.1016/j.scitotenv.2018.11.218 10.1021/acs.est.5b00859 10.1021/acs.est.5b01413 10.5194/acp-14-2015-2014 10.1016/j.isprsjprs.2018.09.006 10.1007/s11356-019-04644-x 10.1175/JCLI-D-16-0609.1 10.1016/j.atmosenv.2011.08.066 10.1038/jes.2015.41 10.1016/j.rse.2018.09.001 10.1021/acs.est.5b05940 10.1016/j.envpol.2018.07.016 10.3389/fnins.2018.01000 10.1016/j.envint.2019.104909 10.1175/BAMS-D-14-00110.1 10.3390/rs8030262 10.1016/j.atmosenv.2014.12.010 10.5194/amt-12-3303-2019 10.5194/acp-14-10013-2014 10.1021/acs.est.7b01210 10.1021/acs.est.9b03799 10.1136/thoraxjnl-2013-204492 10.1016/j.rse.2019.111221 10.1186/s13040-017-0155-3 10.1080/02786820118957 10.1016/j.atmosenv.2006.03.016 10.1021/acs.est.5b06121 10.5194/amt-11-5741-2018 10.1080/10618600.2014.907095 10.1214/aos/1176350057 10.1016/j.envint.2019.04.057 10.1016/j.rse.2017.07.023 10.1016/j.rse.2019.111584 10.1007/s11356-014-3458-7 |
| ContentType | Journal Article |
| Copyright | 2020 The Author(s) Copyright Determination: GOV_PERMITTED Copyright © 2020 The Author(s). Published by Elsevier Ltd.. All rights reserved. |
| Copyright_xml | – notice: 2020 The Author(s) – notice: Copyright Determination: GOV_PERMITTED – notice: Copyright © 2020 The Author(s). Published by Elsevier Ltd.. All rights reserved. |
| DBID | 6I. AAFTH CYE CYI AAYXX CITATION 7X8 7S9 L.6 5PM DOA |
| DOI | 10.1016/j.envint.2020.106143 |
| DatabaseName | ScienceDirect Open Access Titles Elsevier:ScienceDirect:Open Access NASA Scientific and Technical Information NASA Technical Reports Server CrossRef MEDLINE - Academic AGRICOLA AGRICOLA - Academic PubMed Central (Full Participant titles) DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef MEDLINE - Academic AGRICOLA AGRICOLA - Academic |
| DatabaseTitleList | AGRICOLA MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Public Health Environmental Sciences |
| EISSN | 1873-6750 |
| EndPage | 106143 |
| ExternalDocumentID | oai_doaj_org_article_10b913da1bb64b33ac9ad378ab75942c PMC7643812 10_1016_j_envint_2020_106143 20205008643 S0160412020320985 |
| GeographicLocations | California |
| GeographicLocations_xml | – name: California |
| GrantInformation | 4UH3OD023287 P30ES007048 281945.02.80.01.01 |
| GroupedDBID | --- --K --M .~1 0R~ 1B1 1RT 1~. 1~5 29G 4.4 457 4G. 53G 5GY 5VS 6I. 7-5 71M 8P~ 9JM AABNK AACTN AAEDT AAEDW AAFTH AAFWJ AAHBH AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AATTM AAXKI AAXUO ABEFU ABFNM ABFYP ABJNI ABLST ABMAC ABWVN ABXDB ACDAQ ACGFS ACRLP ACRPL ADEZE ADMUD ADNMO ADVLN AEBSH AEGFY AEIPS AEKER AENEX AFJKZ AFPKN AFTJW AFXIZ AGHFR AGUBO AGYEJ AHEUO AHHHB AIEXJ AIKHN AITUG AKIFW AKRWK ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU ASPBG AVWKF AXJTR AZFZN BKOJK BLECG BLXMC BNPGV CS3 DU5 EBS EFJIC EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q GBLVA GROUPED_DOAJ HMC HVGLF HZ~ IHE J1W K-O KCYFY KOM LY9 M41 MO0 N9A O-L O9- OAUVE OK1 OZT P-8 P-9 P2P PC. Q38 R2- RIG RNS ROL RPZ SCC SDF SDG SDP SEN SES SEW SSH SSJ SSZ T5K TN5 WUQ XPP ~02 ~G- AAYWO ACLOT ACVFH ADCNI AEUPX AFPUW AIGII AIIUN AKBMS AKYEP APXCP CYE CYI EFKBS EFLBG ~HD 9DU AAYXX AGQPQ CITATION 7X8 7S9 L.6 5PM |
| ID | FETCH-LOGICAL-c560t-a61e5bde3266ca7c30a815587452a384a2d4110c9e6659341c524f540307f1643 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 65 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000580632000058&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0160-4120 1873-6750 |
| IngestDate | Fri Oct 03 12:45:57 EDT 2025 Tue Sep 30 16:01:17 EDT 2025 Wed Oct 01 14:29:47 EDT 2025 Wed Oct 01 14:16:59 EDT 2025 Sat Nov 29 07:26:34 EST 2025 Tue Nov 18 21:01:38 EST 2025 Fri Nov 21 15:49:36 EST 2025 Sun Apr 06 06:53:03 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Wildfires High spatiotemporal resolution Air pollution exposure PM2.5 Machine learning California Remote sensing Air Quality Air Pollution Exposure Wildfire Pm2.5 Remote Sensing High Spatiotemporal Resolution Machine Learning |
| Language | English |
| License | This is an open access article under the CC BY-NC-ND license. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c560t-a61e5bde3266ca7c30a815587452a384a2d4110c9e6659341c524f540307f1643 |
| Notes | GSFC Goddard Space Flight Center ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 Crystal McClure: Resource, Data curation Luke D. Oman: Resource, Data curation Rima Habre: Project administration, Investigation, Conceptualization, Writing - Review & Editing Frank Gilliland: Project administration, Writing - Review Carrie Breton: Project administration, Writing - Review Jun Wu: Resources, Data curation, Writing - Review & Editing Lianfa Li: Conceptualization, Methodology, Formal Analysis, Validation, Writing - Original Draft and Revising Mariam Girguis: Investigation, Data curation Frederick Lurmann: Conceptualization, Resource, Data curation, Writing - Review & Editing Nathan Pavlovic: Resource, Data curation, Writing - Review & Editing Meredith Franklin: Conceptualization, Resource, Writing - Review & Editing |
| ORCID | 0000-0003-2127-3940 0000-0003-2103-1706 0000-0002-2693-7112 0000-0001-7477-5528 0000-0002-5487-2598 |
| OpenAccessLink | https://doaj.org/article/10b913da1bb64b33ac9ad378ab75942c |
| PMID | 32980736 |
| PQID | 2446994248 |
| PQPubID | 23479 |
| PageCount | 1 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_10b913da1bb64b33ac9ad378ab75942c pubmedcentral_primary_oai_pubmedcentral_nih_gov_7643812 proquest_miscellaneous_2552011859 proquest_miscellaneous_2446994248 crossref_primary_10_1016_j_envint_2020_106143 crossref_citationtrail_10_1016_j_envint_2020_106143 nasa_ntrs_20205008643 elsevier_sciencedirect_doi_10_1016_j_envint_2020_106143 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-12-01 |
| PublicationDateYYYYMMDD | 2020-12-01 |
| PublicationDate_xml | – month: 12 year: 2020 text: 2020-12-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Goddard Space Flight Center |
| PublicationPlace_xml | – name: Goddard Space Flight Center |
| PublicationTitle | Environment international |
| PublicationYear | 2020 |
| Publisher | Elsevier Ltd Elsevier |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier |
| References | Lv, Hu, Chang, Russell, Bai (b0300) 2016; 50 Goldstein, Kapelner, Bleich, Pitkin (b0140) 2015; 24 Livingston, Redemann, Shinozuka, Johnson, Russell, Zhang, Mattoo, Remer, Levy, Munchak, Ramachandran (b0285) 2014; 14 Zheng, Wang, Wang, Zhang, Wu, Zhang, Yu, Guan (b0455) 2019; 12 Stein, Draxler, Rolph, Stunder, Cohen, Ngan (b0350) 2015; 96 Beckerman, Jerrett, Serre, Martin, Lee, van Donkelaar, Ross, Su, Burnett (b0025) 2013; 47 Li, Zhang, Meng, Fang, Ge, Wang, Wang, Wu, Kan (b0260) 2018; 217 Li, Girguis, Lurmann, Wu, Urman, Rappaport, Ritz, Franklin, Breton, Gilliland, Habre (b0265) 2019; 128 Wang, Jia, Xia, Wu, Wei, Shang, Yang, Xue, Dou (b0395) 2019; 12 Finkenstadt, Held, Isham (b0110) 2007 Dennison, Brewer, Arnold, Moritz (b0065) 2014; 41 Biancofiore, Busilacchio, Verdecchia, Tomassetti, Aruffo, Bianco, Di Tommaso, Colangeli, Rosatelli, Di Carlo (b0035) 2017; 8 Fast, Allan, Bahreini, Craven, Emmons, Ferrare, Hayes, Hodzic, Holloway, Hostetler, Jimenez, Jonsson, Liu, Liu, Metcalf, Middlebrook, Nowak, Pekour, Perring, Russell, Sedlacek, Seinfeld, Setyan, Shilling, Shrivastava, Springston, Song, Subramanian, Taylor, Vinoj, Yang, Zaveri, Zhang (b0100) 2014; 14 NASA, 2018. MERRA-2 GMI In. Li, Franklin, Girguis, Lurmann, Wu, Pavlovic, Breton, Gilliland, Habre (b0255) 2020; 237 Goodfellow, Bengio, Courville (b0145) 2016 WHO, 2013b. Review of evidence on health aspects of air pollution—REVIHAAP project: Final technical report. The WHO European Centre for Environment and Health, Bonn, Switzerland. Carlstein (b0050) 1986; 14 He, Zhang, Ren, Sun (b0160) 2016 Allen, Adar, Avol, Cohen, Curl, Larson, Liu, Sheppard, Kaufman (b0010) 2012; 120 Kloog, Koutrakis, Coull, Lee, Schwartz (b0200) 2011; 45 Ichoku, Ellison (b0185) 2014; 14 Atkinson, Kang, Anderson, Mills, Walton (b0015) 2014; 69 Lee, Chatfield, Strawa (b0235) 2016; 50 Li, Carlson, Lacis (b0250) 2015; 102 Bai, Wu, Qin, Zhang, Shen, Zhou (b0020) 2016; 8 Xiao, Wang, Chang, Meng, Geng, Lyapustin, Liu (b0425) 2017; 199 Monn (b0320) 2001; 35 Thompson, Calkin (b0370) 2011; 92 Wei, Huang, Li, Xue, Peng, Sun, Cribb (b0405) 2019; 231 Larsen, Reich, Ruminski, Rappold (b0225) 2018; 28 Brauer, Freedman, Frostad, van Donkelaar, Martin, Dentener, van Dingenen, Estep, Amini, Apte, Balakrishnan, Barregard, Broday, Feigin, Ghosh, Hopke, Knibbs, Kokubo, Liu, Ma, Morawska, Sangrador, Shaddick, Anderson, Vos, Forouzanfar, Burnett, Cohen (b0040) 2016; 50 Girguis, M.S., Li, L.F., Lurmann, F., Wu, J., Urman, R., Rappaport, E., Breton, C., Gilliland, F., Stram, D., & Habre, R., 2020. Exposure measurement error in air pollution studies: the impact of shared, multiplicative measurement error on epidemiological health risk estimates. Air Qual. Atmos. Health, accepted. Kloog (b0195) 2016; 26 Chicco (b0055) 2017; 10 EPA, 2014. Guidance for PM2.s Permit Modeling. In: United States Environmental Protection Agency. Lyapustin, Korkin, Wang, Quayle, Laszlo (b0305) 2012; 12 Gupta, Christopher, Wang, Gehrig, Lee, Kumar (b0155) 2006; 40 Hu, Belle, Meng, Wildani, Waller, Strickland, Liu (b0170) 2017; 51 Knote, Tuccella, Curci, Emmons, Orlando, Madronich, Baro, Jimenez-Guerrero, Luecken, Hogrefe, Forkel, Werhahn, Hirtl, Perez, San Jose, Giordano, Brunner, Yahya, Zhang (b0205) 2015; 115 Lee, Li, Kim, Kokhanovsky (b0240) 2009 Chu, Liu, Li, Liu, Lu, Lu, Mao, Chen, Li, Ren, Liu, Tian, Zhu, Xiang (b0060) 2016; 7 Di, Kloog, Koutrakis, Lyapustin, Wang, Schwartz (b0075) 2016; 50 Lee (b0230) 2019; 53 Brokamp, Jandarov, Rao, LeMasters, Ryan (b0045) 2017; 151 Koelemeijer, Homan, Matthijsen (b0210) 2006; 40 van Donkelaar, Martin, Park (b0390) 2006; 111 Lyapustin, Wang, Korkin, Huang (b0315) 2018; 11 Hu, Waller, Lyapustin, Wang, Al-Hamdan, Crosson, Estes, Estes, Quattrochi, Puttaswamy, Liu (b0175) 2014; 140 Larsen, A., Yang, S., Reich, B.J., Rappold, A.G., 2020. A spatial causal analysis of wildland fire-contributed PM2. 5 using numerical model output. arXiv preprint arXiv:2003.06037. Liu, Paciorek, Koutrakis (b0280) 2009; 117 Lee, Kloog, Chudnovsky, Lyapustin, Wang, Melly, Coull, Koutrakis, Schwartz (b0245) 2015; 26 Zhai, Li, Zou, Sang, Fang, Xu (b0450) 2018; 181 Su, Li, Kahn (b0360) 2018; 18 Lyapustin, Wang, Laszlo, Kahn, Korkin, Remer, Levy, Reid (b0310) 2011; 116 Xie, Wang, Zhang, Dong, Lv, Bai (b0430) 2015; 49 Randles, da Silva, Buchard, Colarco, Darmenov, Govindaraju, Smirnov, Holben, Ferrare, Hair, Shinozuka, Flynn (b0335) 2017; 30 Wang, Chen, Tao, Zhang, Su (b0400) 2010; 114 Friedman (b0115) 2001 WHO, 2013a. Health Effects of Particular Matter: Policy implications for countries in eastern Europe, Caucasus and central Asia. Zou, Hastie (b0465) 2005; 67 He, Zhang, Ren, Sun (b0165) 2016 Western Regional Air Partnership, 2005. 2002 Fire Emission Inventory for the WRAP Region – Phase II, Project No. 178-6. pp. 1–97. Tolocka, Solomon, Mitchell, Norris, Gemmill, Wiener, Vanderpool, Homolya, Rice (b0380) 2001; 34 Abatzoglou (b0005) 2011; 2011 Tai, Mickley, Jacob (b0365) 2010; 44 Liang, Zhang, Zhao, Ruan, Lian, Fan (b0270) 2014; 32 Fruin, Urman, Lurmann, McConnell, Gauderman, Rappaport, Franklin, Gilliland, Shafer, Gorski, Avol (b0120) 2014; 83 Lundberg, S.M., Lee, S.-I., 2017. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 4765–4774. Kunzli, Jerrett, Garcia-Esteban, Basagana, Beckermann, Gilliland, Medina, Peters, Hodis, Mack (b0215) 2010; 5 Xing, Xu, Shi, Lian (b0435) 2016; 8 Feng, Li, Zhu, Hou, Jin, Wang (b0105) 2015; 107 NIST/SEMATECH, 2016. e-Handbook of Statistical Methods. Huang, Xiao, Meng, Geng, Wang, Lyapustin, Gu, Liu (b0180) 2018; 242 Lu, Xu, Cheng, Dong, Guo, Jiang, Zheng (b0290) 2015; 136 Toth, Zhang, Campbell, Hyer, Reid, Shi, Westphal (b0385) 2014; 14 EPA (b0090) 2018 Ester, Kriegel, Sander, Xu (b0095) 1996 Just, Wright, Schwartz, Coull, Baccarelli, Tellez-Rojo, Moody, Wang, Lyapustin, Kloog (b0190) 2015; 49 Strode, Ziemke, Oman, Lamsal, Olsen, Liu (b0355) 2019; 199 Lippmann (b0275) 2014; 44 Shirmohammadi, Hasheminassab, Saffari, Schauer, Delfino, Sioutas (b0345) 2016; 541 Guo, Tang, Gong, Zhang (b0150) 2017; 198 Yang, Jin, Danielson, Homer, Gass, Bender, Case, Costello, Dewitz, Fry, Funk, Granneman, Liknes, Rigge, Xian (b0440) 2018; 146 Girguis, Li, Lurmann, Wu, Urman, Rappaport, Breton, Gilliland, Stram, Habre (b0130) 2019; 125 Zhu, Liu, Chen, Yao, Che, Cao (b0460) 2015; 22 Yuan, Zhang, Gao, Tian (b0445) 2019; 26 Thomson (b0375) 2010; 4 Reid, Brauer, Johnston, Jerrett, Balmes, Elliott (b0340) 2016; 124 EPA, 2017. Health and Environmental Effects of Particulate Matter (PM). Fu, Guo, Cheung, Yung (b0125) 2019; 655 Bhandari, A., 2020. Feature Scaling for Machine Learning: Understanding the Difference Between Normalization vs. Standardization. Di, Amini, Shi, Kloog, Silvern, Kelly, Sabath, Choirat, Koutrakis, Lyapustin, Wang, Mickley, Schwartz (b0070) 2019; 130 Girguis (10.1016/j.envint.2020.106143_b0130) 2019; 125 Randles (10.1016/j.envint.2020.106143_b0335) 2017; 30 Fast (10.1016/j.envint.2020.106143_b0100) 2014; 14 Lippmann (10.1016/j.envint.2020.106143_b0275) 2014; 44 Lv (10.1016/j.envint.2020.106143_b0300) 2016; 50 Allen (10.1016/j.envint.2020.106143_b0010) 2012; 120 Chu (10.1016/j.envint.2020.106143_b0060) 2016; 7 Liang (10.1016/j.envint.2020.106143_b0270) 2014; 32 10.1016/j.envint.2020.106143_b0325 Feng (10.1016/j.envint.2020.106143_b0105) 2015; 107 Monn (10.1016/j.envint.2020.106143_b0320) 2001; 35 Lee (10.1016/j.envint.2020.106143_b0235) 2016; 50 Lyapustin (10.1016/j.envint.2020.106143_b0310) 2011; 116 Thompson (10.1016/j.envint.2020.106143_b0370) 2011; 92 Li (10.1016/j.envint.2020.106143_b0250) 2015; 102 Shirmohammadi (10.1016/j.envint.2020.106143_b0345) 2016; 541 Atkinson (10.1016/j.envint.2020.106143_b0015) 2014; 69 He (10.1016/j.envint.2020.106143_b0160) 2016 Fruin (10.1016/j.envint.2020.106143_b0120) 2014; 83 Strode (10.1016/j.envint.2020.106143_b0355) 2019; 199 10.1016/j.envint.2020.106143_b0330 Xie (10.1016/j.envint.2020.106143_b0430) 2015; 49 Wang (10.1016/j.envint.2020.106143_b0400) 2010; 114 Friedman (10.1016/j.envint.2020.106143_b0115) 2001 Lee (10.1016/j.envint.2020.106143_b0230) 2019; 53 10.1016/j.envint.2020.106143_b0295 Zou (10.1016/j.envint.2020.106143_b0465) 2005; 67 Carlstein (10.1016/j.envint.2020.106143_b0050) 1986; 14 10.1016/j.envint.2020.106143_b0135 Just (10.1016/j.envint.2020.106143_b0190) 2015; 49 10.1016/j.envint.2020.106143_b0410 Gupta (10.1016/j.envint.2020.106143_b0155) 2006; 40 Li (10.1016/j.envint.2020.106143_b0255) 2020; 237 10.1016/j.envint.2020.106143_b0415 Reid (10.1016/j.envint.2020.106143_b0340) 2016; 124 Ester (10.1016/j.envint.2020.106143_b0095) 1996 Xiao (10.1016/j.envint.2020.106143_b0425) 2017; 199 Lyapustin (10.1016/j.envint.2020.106143_b0305) 2012; 12 Zhu (10.1016/j.envint.2020.106143_b0460) 2015; 22 Thomson (10.1016/j.envint.2020.106143_b0375) 2010; 4 Chicco (10.1016/j.envint.2020.106143_b0055) 2017; 10 Tai (10.1016/j.envint.2020.106143_b0365) 2010; 44 Wei (10.1016/j.envint.2020.106143_b0405) 2019; 231 Li (10.1016/j.envint.2020.106143_b0265) 2019; 128 Lu (10.1016/j.envint.2020.106143_b0290) 2015; 136 EPA (10.1016/j.envint.2020.106143_b0090) 2018 Knote (10.1016/j.envint.2020.106143_b0205) 2015; 115 Di (10.1016/j.envint.2020.106143_b0070) 2019; 130 Li (10.1016/j.envint.2020.106143_b0260) 2018; 217 Hu (10.1016/j.envint.2020.106143_b0170) 2017; 51 10.1016/j.envint.2020.106143_b0220 Abatzoglou (10.1016/j.envint.2020.106143_b0005) 2011; 2011 10.1016/j.envint.2020.106143_b0420 Liu (10.1016/j.envint.2020.106143_b0280) 2009; 117 Brokamp (10.1016/j.envint.2020.106143_b0045) 2017; 151 Koelemeijer (10.1016/j.envint.2020.106143_b0210) 2006; 40 Stein (10.1016/j.envint.2020.106143_b0350) 2015; 96 Dennison (10.1016/j.envint.2020.106143_b0065) 2014; 41 Beckerman (10.1016/j.envint.2020.106143_b0025) 2013; 47 Goodfellow (10.1016/j.envint.2020.106143_b0145) 2016 Goldstein (10.1016/j.envint.2020.106143_b0140) 2015; 24 Tolocka (10.1016/j.envint.2020.106143_b0380) 2001; 34 Yang (10.1016/j.envint.2020.106143_b0440) 2018; 146 Zhai (10.1016/j.envint.2020.106143_b0450) 2018; 181 Huang (10.1016/j.envint.2020.106143_b0180) 2018; 242 Yuan (10.1016/j.envint.2020.106143_b0445) 2019; 26 Hu (10.1016/j.envint.2020.106143_b0175) 2014; 140 Xing (10.1016/j.envint.2020.106143_b0435) 2016; 8 Brauer (10.1016/j.envint.2020.106143_b0040) 2016; 50 Lyapustin (10.1016/j.envint.2020.106143_b0315) 2018; 11 Bai (10.1016/j.envint.2020.106143_b0020) 2016; 8 Lee (10.1016/j.envint.2020.106143_b0240) 2009 Su (10.1016/j.envint.2020.106143_b0360) 2018; 18 Livingston (10.1016/j.envint.2020.106143_b0285) 2014; 14 10.1016/j.envint.2020.106143_b0030 Kloog (10.1016/j.envint.2020.106143_b0195) 2016; 26 Kunzli (10.1016/j.envint.2020.106143_b0215) 2010; 5 Guo (10.1016/j.envint.2020.106143_b0150) 2017; 198 Biancofiore (10.1016/j.envint.2020.106143_b0035) 2017; 8 Fu (10.1016/j.envint.2020.106143_b0125) 2019; 655 He (10.1016/j.envint.2020.106143_b0165) 2016 Wang (10.1016/j.envint.2020.106143_b0395) 2019; 12 Zheng (10.1016/j.envint.2020.106143_b0455) 2019; 12 Di (10.1016/j.envint.2020.106143_b0075) 2016; 50 Lee (10.1016/j.envint.2020.106143_b0245) 2015; 26 Larsen (10.1016/j.envint.2020.106143_b0225) 2018; 28 Toth (10.1016/j.envint.2020.106143_b0385) 2014; 14 van Donkelaar (10.1016/j.envint.2020.106143_b0390) 2006; 111 10.1016/j.envint.2020.106143_b0080 Ichoku (10.1016/j.envint.2020.106143_b0185) 2014; 14 Kloog (10.1016/j.envint.2020.106143_b0200) 2011; 45 Finkenstadt (10.1016/j.envint.2020.106143_b0110) 2007 10.1016/j.envint.2020.106143_b0085 |
| References_xml | – volume: 7 year: 2016 ident: b0060 article-title: A review on predicting ground PM2.5 concentration using satellite aerosol optical depth publication-title: Atmosphere – volume: 51 start-page: 6936 year: 2017 end-page: 6944 ident: b0170 article-title: Estimating PM2.5 concentrations in the conterminous United States using the random forest approach publication-title: Environ. Sci. Technol. – volume: 14 start-page: 1171 year: 1986 end-page: 1179 ident: b0050 article-title: The use of subseries values for estimating the variance of a general statistic from a stationary sequence publication-title: Ann. Statist. – volume: 96 start-page: 2059 year: 2015 end-page: 2077 ident: b0350 article-title: Noaa's hysplit atmospheric transport and dispersion modeling system publication-title: Bull. Am. Meteorol. Soc. – volume: 116 year: 2011 ident: b0310 article-title: Multiangle implementation of atmospheric correction (MAIAC): 2. Aerosol algorithm publication-title: J. Geophys. Res.-Atmos. – volume: 41 start-page: 2928 year: 2014 end-page: 2933 ident: b0065 article-title: Large wildfire trends in the western United States, 1984–2011 publication-title: Geophys. Res. Lett. – year: 2009 ident: b0240 article-title: Atmospheric aerosol monitoring from satellite observations: a history of three decades publication-title: Atmospheric and Biological Environmental Monitoring – volume: 26 start-page: 377 year: 2015 end-page: 384 ident: b0245 article-title: Spatiotemporal prediction of fine particulate matter using high-resolution satellite images in the southeastern U.S. 2003–2011 publication-title: J. Expo. Sci. Environ. Epidemiol. – volume: 541 start-page: 1083 year: 2016 end-page: 1096 ident: b0345 article-title: Fine and ultrafine particulate organic carbon in the Los Angeles basin: trends in sources and composition publication-title: Sci. Total Environ. – volume: 114 start-page: 50 year: 2010 end-page: 63 ident: b0400 article-title: Satellite-based estimation of regional particulate matter (PM) in Beijing using vertical-and-RH correcting method publication-title: Remote Sens. Environ. – volume: 8 start-page: 652 year: 2017 end-page: 659 ident: b0035 article-title: Recursive neural network model for analysis and forecast of PM10 and PM2.5 publication-title: Atmos. Pollut. Res. – volume: 32 start-page: 2130 year: 2014 end-page: 2141 ident: b0270 article-title: Effect of exposure to PM2.5 on blood pressure: a systematic review and meta-analysis publication-title: J. Hypertens. – volume: 40 start-page: 5880 year: 2006 end-page: 5892 ident: b0155 article-title: Satellite remote sensing of particulate matter and air quality assessment over global cities publication-title: Atmos. Environ. – reference: Western Regional Air Partnership, 2005. 2002 Fire Emission Inventory for the WRAP Region – Phase II, Project No. 178-6. pp. 1–97. – volume: 49 start-page: 8576 year: 2015 end-page: 8584 ident: b0190 article-title: Using high-resolution satellite aerosol optical depth to estimate daily PM2. 5 geographical distribution in Mexico City publication-title: Environ. Sci. Technol. – start-page: 770 year: 2016 end-page: 778 ident: b0160 article-title: Deep residual learning for image recognition publication-title: 2016 IEEE Conference on Computer Vision and Pattern Recognition (Cvpr) – volume: 12 start-page: 3303 year: 2019 end-page: 3315 ident: b0395 article-title: Relationship analysis of PM 2.5 and boundary layer height using an aerosol and turbulence detection lidar publication-title: Atmos. Meas. Tech. – volume: 5 year: 2010 ident: b0215 article-title: Ambient air pollution and the progression of atherosclerosis in adults publication-title: PLoS ONE – volume: 26 start-page: 13963 year: 2019 end-page: 13983 ident: b0445 article-title: Maternal fine particulate matter (PM2.5) exposure and adverse birth outcomes: an updated systematic review based on cohort studies publication-title: Environ. Sci. Pollut. Res. – reference: NASA, 2018. MERRA-2 GMI In. – start-page: 226 year: 1996 end-page: 231 ident: b0095 article-title: A density-based algorithm for discovering clusters in large spatial databases with noise publication-title: KDD'96: Proceedings of the Second International Conference on Knowledge Discovery and Data Mining – volume: 199 start-page: 323 year: 2019 end-page: 333 ident: b0355 article-title: Global changes in the diurnal cycle of surface ozone publication-title: Atmos. Environ. – reference: Bhandari, A., 2020. Feature Scaling for Machine Learning: Understanding the Difference Between Normalization vs. Standardization. – reference: Girguis, M.S., Li, L.F., Lurmann, F., Wu, J., Urman, R., Rappaport, E., Breton, C., Gilliland, F., Stram, D., & Habre, R., 2020. Exposure measurement error in air pollution studies: the impact of shared, multiplicative measurement error on epidemiological health risk estimates. Air Qual. Atmos. Health, accepted. – volume: 102 start-page: 260 year: 2015 end-page: 273 ident: b0250 article-title: How well do satellite AOD observations represent the spatial and temporal variability of PM2.5 concentration for the United States? publication-title: Atmos. Environ. – volume: 140 start-page: 220 year: 2014 end-page: 232 ident: b0175 article-title: Estimating ground-level PM2.5 concentrations in the Southeastern United States using MAIAC AOD retrievals and a two-stage model publication-title: Remote Sens. Environ. – volume: 53 start-page: 12774 year: 2019 end-page: 12783 ident: b0230 article-title: Benefits of high resolution PM2.5 prediction using satellite MAIAC AOD and land use regression for exposure assessment: California examples publication-title: Environ. Sci. Technol. – volume: 83 start-page: 211 year: 2014 end-page: 219 ident: b0120 article-title: Spatial variation in particulate matter components over a large urban area publication-title: Atmos. Environ. – volume: 14 start-page: 6643 year: 2014 end-page: 6667 ident: b0185 article-title: Global top-down smoke-aerosol emissions estimation using satellite fire radiative power measurements publication-title: Atmos. Chem. Phys. – volume: 14 start-page: 2015 year: 2014 end-page: 2038 ident: b0285 article-title: Comparison of MODIS 3 km and 10 km resolution aerosol optical depth retrievals over land with airborne sunphotometer measurements during ARCTAS summer 2008 publication-title: Atmos. Chem. Phys. – year: 2007 ident: b0110 article-title: Statistical Methods for Spatio-Temporal Systems – volume: 50 start-page: 4712 year: 2016 end-page: 4721 ident: b0075 article-title: Assessing PM2.5 exposures with high spatiotemporal resolution across the continental United States publication-title: Environ Sci Technol – year: 2018 ident: b0090 article-title: 2014 National Emissions Inventory, version 2 Technical Support Document – volume: 128 start-page: 310 year: 2019 end-page: 323 ident: b0265 article-title: Cluster-based bagging of constrained mixed-effects models for high spatiotemporal resolution nitrogen oxides prediction over large regions publication-title: Environ. Int. – volume: 11 start-page: 5741 year: 2018 end-page: 5765 ident: b0315 article-title: MODIS collection 6 MAIAC algorithm publication-title: Atmos. Meas. Tech. – volume: 40 start-page: 5304 year: 2006 end-page: 5315 ident: b0210 article-title: Comparison of spatial and temporal variations of aerosol optical thickness and particulate matter over Europe publication-title: Atmos. Environ. – volume: 44 start-page: 299 year: 2014 end-page: 347 ident: b0275 article-title: Toxicological and epidemiological studies of cardiovascular effects of ambient air fine particulate matter (PM2.5) and its chemical components: Coherence and public health implications publication-title: Crit. Rev. Toxicol. – volume: 107 start-page: 118 year: 2015 end-page: 128 ident: b0105 article-title: Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation publication-title: Atmos. Environ. – volume: 50 start-page: 4752 year: 2016 end-page: 4759 ident: b0300 article-title: Improving the accuracy of daily PM2.5 distributions derived from the fusion of ground-level measurements with aerosol optical depth observations, a case study in north China publication-title: Environ. Sci. Technol. – volume: 26 start-page: 572 year: 2016 end-page: 577 ident: b0195 article-title: Fine particulate matter (PM2.5) association with peripheral artery disease admissions in northeastern United States publication-title: Int. J. Environ. Health Res. – volume: 181 start-page: 145 year: 2018 end-page: 154 ident: b0450 article-title: An improved geographically weighted regression model for PM2.5 concentration estimation in large areas publication-title: Atmos. Environ. – volume: 115 start-page: 553 year: 2015 end-page: 568 ident: b0205 article-title: Influence of the choice of gas-phase mechanism on predictions of key gaseous pollutants during the AQMEII phase-2 intercomparison publication-title: Atmos. Environ. – volume: 50 start-page: 6546 year: 2016 end-page: 6555 ident: b0235 article-title: Enhancing the applicability of satellite remote sensing for PM2.5 estimation using MODIS deep blue AOD and land use regression in California, United States publication-title: Environ. Sci. Technol. – volume: 10 year: 2017 ident: b0055 article-title: Ten quick tips for machine learning in computational biology publication-title: Biodata Min. – reference: Lundberg, S.M., Lee, S.-I., 2017. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst. 4765–4774. – volume: 8 start-page: 262 year: 2016 ident: b0020 article-title: A geographically and temporallyweighted regression model for ground-level PM2.5 estimation from satellite-derived 500 m resolution AOD publication-title: Remote Sens. – volume: 237 year: 2020 ident: b0255 article-title: Spatiotemporal imputation of MAIAC AOD using deep learning with downscaling publication-title: Remote Sens. Environ. – volume: 231 year: 2019 ident: b0405 article-title: Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random forest approach publication-title: Remote Sens. Environ. – volume: 242 start-page: 675 year: 2018 end-page: 683 ident: b0180 article-title: Predicting monthly high-resolution PM2.5 concentrations with random forest model in the North China Plain publication-title: Environ. Pollut. – volume: 92 start-page: 1895 year: 2011 end-page: 1909 ident: b0370 article-title: Uncertainty and risk in wildland fire management: a review publication-title: J. Environ. Manage. – volume: 67 start-page: 768 year: 2005 ident: b0465 article-title: Regularization and variable selection via the elastic net (vol B 67, pg 301, 2005) publication-title: J. Roy. Stat. Soc. Ser. B-Stat. Methodology – volume: 14 start-page: 10013 year: 2014 end-page: 10060 ident: b0100 article-title: Modeling regional aerosol and aerosol precursor variability over California and its sensitivity to emissions and long-range transport during the 2010 CalNex and CARES campaigns publication-title: Atmos. Chem. Phys. – start-page: 1189 year: 2001 end-page: 1232 ident: b0115 article-title: Greedy function approximation: a gradient boosting machine publication-title: Ann. Stat. – volume: 24 start-page: 44 year: 2015 end-page: 65 ident: b0140 article-title: Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation publication-title: J. Comput. Graphical Stat. – volume: 8 start-page: E69 year: 2016 end-page: E74 ident: b0435 article-title: The impact of PM2.5 on the human respiratory system publication-title: J. Thoracic Disease – volume: 2011 year: 2011 ident: b0005 article-title: Development of gridded surface meteorological datafor ecological applications and modelling publication-title: Int. J. Climatol. – volume: 30 start-page: 6823 year: 2017 end-page: 6850 ident: b0335 article-title: The MERRA-2 aerosol reanalysis, 1980 onward. Part I: System description and data assimilation evaluation publication-title: J. Clim. – volume: 136 start-page: 196 year: 2015 end-page: 204 ident: b0290 article-title: Systematic review and meta-analysis of the adverse health effects of ambient PM2. 5 and PM10 pollution in the Chinese population publication-title: Environ. Res. – volume: 199 start-page: 437 year: 2017 end-page: 446 ident: b0425 article-title: Full-coverage high-resolution daily PM2.5 estimation using MAIAC AOD in the Yangtze River Delta of China publication-title: Remote Sens. Environ. – volume: 18 start-page: 15921 year: 2018 end-page: 15935 ident: b0360 article-title: Relationships between the planetary boundary layer height and surface pollutants derived from lidar observations over China: regional pattern and influencing factors publication-title: Atmos. Chem. Phys. – reference: NIST/SEMATECH, 2016. e-Handbook of Statistical Methods. – volume: 12 year: 2019 ident: b0455 article-title: Gestational exposure to particulate matter 2.5 (PM2.5) leads to spatial memory dysfunction and neurodevelopmental impairment in hippocampus of mice offspring publication-title: Front. Neurosci. – volume: 198 start-page: 140 year: 2017 end-page: 149 ident: b0150 article-title: Estimating ground-level PM2.5 concentrations in Beijing using a satellite-based geographically and temporally weighted regression model publication-title: Remote Sens. Environ. – volume: 217 start-page: 573 year: 2018 end-page: 586 ident: b0260 article-title: Estimation of PM2. 5 concentrations at a high spatiotemporal resolution using constrained mixed-effect bagging models with MAIAC aerosol optical depth publication-title: Remote Sens. Environ. – reference: EPA, 2017. Health and Environmental Effects of Particulate Matter (PM). – volume: 49 start-page: 12280 year: 2015 end-page: 12288 ident: b0430 article-title: Daily estimation of ground-level PM2.5 concentrations over Beijing using 3 km resolution MODIS AOD publication-title: Environ. Sci. Technol. – volume: 146 start-page: 108 year: 2018 end-page: 123 ident: b0440 article-title: A new generation of the United States National Land Cover Database: Requirements, research priorities, design, and implementation strategies publication-title: ISPRS J. Photogramm. Remote Sens. – volume: 130 year: 2019 ident: b0070 article-title: An ensemble-based model of PM2.5 concentration across the contiguous United States with high spatiotemporal resolution publication-title: Environ. Int. – volume: 44 start-page: 3976 year: 2010 end-page: 3984 ident: b0365 article-title: Correlations between fine particulate matter (PM2. 5) and meteorological variables in the United States: implications for the sensitivity of PM2. 5 to climate change publication-title: Atmos. Environ. – start-page: 630 year: 2016 end-page: 645 ident: b0165 article-title: Identity Mappings in Deep Residual Networks publication-title: Computer Vision - Eccv 2016 Pt Iv 9908 – reference: WHO, 2013a. Health Effects of Particular Matter: Policy implications for countries in eastern Europe, Caucasus and central Asia. – volume: 120 start-page: 824 year: 2012 end-page: 830 ident: b0010 article-title: Modeling the residential infiltration of outdoor PM2.5 in the Multi-Ethnic Study of Atherosclerosis and Air Pollution (MESA Air) publication-title: Environ. Health Perspect. – volume: 124 start-page: 1334 year: 2016 end-page: 1343 ident: b0340 article-title: Critical review of health impacts of wildfire smoke exposure publication-title: Environ. Health Perspect. – volume: 28 start-page: 319 year: 2018 end-page: 327 ident: b0225 article-title: Impacts of fire smoke plumes on regional air quality, 2006–2013 publication-title: J. Exposure Sci. Environ. Epidemiol. – volume: 151 start-page: 1 year: 2017 end-page: 11 ident: b0045 article-title: Exposure assessment models for elemental components of particulate matter in an urban environment: a comparison of regression and random forest approaches publication-title: Atmos. Environ. – volume: 45 start-page: 6267 year: 2011 end-page: 6275 ident: b0200 article-title: Assessing temporally and spatially resolved PM2.5 exposures for epidemiological studies using satellite aerosol optical depth measurements publication-title: Atmos. Environ. – volume: 50 start-page: 79 year: 2016 end-page: 88 ident: b0040 article-title: Ambient air pollution exposure estimation for the global burden of disease 2013 publication-title: Environ. Sci. Technol. – volume: 125 start-page: 97 year: 2019 end-page: 106 ident: b0130 article-title: Exposure measurement error in air pollution studies: a framework for assessing shared, multiplicative measurement error in ensemble learning estimates of nitrogen oxides publication-title: Environ. Int. – year: 2016 ident: b0145 article-title: Deep Learning – volume: 117 start-page: 886 year: 2009 end-page: 892 ident: b0280 article-title: Estimating regional spatial and temporal variability of PM2.5 concentrations using satellite data, meteorology, and land use information publication-title: Environ. Health Perspect. – volume: 111 year: 2006 ident: b0390 article-title: Estimating ground-level PM2.5 using aerosol optical depth determined from satellite remote sensing publication-title: J. Geophys. Res.-Atmos. – volume: 12 start-page: 9679 year: 2012 end-page: 9686 ident: b0305 article-title: Discrimination of biomass burning smoke and clouds in MAIAC algorithm publication-title: Atmos. Chem. Phys. – volume: 4 year: 2010 ident: b0375 article-title: Neocortical layer 6, a review publication-title: Front. Neuroanat. – volume: 34 start-page: 88 year: 2001 end-page: 96 ident: b0380 article-title: East versus West in the US: chemical characteristics of PM2.5 during the winter of 1999 publication-title: Aerosol Sci. Technol. – reference: WHO, 2013b. Review of evidence on health aspects of air pollution—REVIHAAP project: Final technical report. The WHO European Centre for Environment and Health, Bonn, Switzerland. – volume: 22 start-page: 3383 year: 2015 end-page: 3396 ident: b0460 article-title: Maternal exposure to fine particulate matter (PM2.5) and pregnancy outcomes: a meta-analysis publication-title: Environ. Sci. Pollut. Res. – volume: 69 start-page: 660 year: 2014 end-page: 665 ident: b0015 article-title: Epidemiological time series studies of PM2. 5 and daily mortality and hospital admissions: a systematic review and meta-analysis publication-title: Thorax – reference: EPA, 2014. Guidance for PM2.s Permit Modeling. In: United States Environmental Protection Agency. – reference: Larsen, A., Yang, S., Reich, B.J., Rappold, A.G., 2020. A spatial causal analysis of wildland fire-contributed PM2. 5 using numerical model output. arXiv preprint arXiv:2003.06037. – volume: 14 start-page: 6049 year: 2014 end-page: 6062 ident: b0385 article-title: Impact of data quality and surface-to-column representativeness on the PM2.5/satellite AOD relationship for the contiguous United States publication-title: Atmos. Chem. Phys. – volume: 47 start-page: 7233 year: 2013 end-page: 7241 ident: b0025 article-title: A hybrid approach to estimating national scale spatiotemporal variability of PM2.5 in the contiguous United States publication-title: Environ. Sci. Technol. – volume: 655 start-page: 1240 year: 2019 end-page: 1248 ident: b0125 article-title: The association between PM2.5 exposure and neurological disorders: a systematic review and meta-analysis publication-title: Sci. Total Environ. – volume: 35 start-page: 1 year: 2001 end-page: 32 ident: b0320 article-title: Exposure assessment of air pollutants: a review on spatial heterogeneity and indoor/outdoor/personal exposure to suspended particulate matter, nitrogen dioxide and ozone publication-title: Atmos. Environ. – volume: 12 start-page: 9679 year: 2012 ident: 10.1016/j.envint.2020.106143_b0305 article-title: Discrimination of biomass burning smoke and clouds in MAIAC algorithm publication-title: Atmos. Chem. Phys. doi: 10.5194/acp-12-9679-2012 – ident: 10.1016/j.envint.2020.106143_b0325 – volume: 83 start-page: 211 year: 2014 ident: 10.1016/j.envint.2020.106143_b0120 article-title: Spatial variation in particulate matter components over a large urban area publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2013.10.063 – volume: 199 start-page: 323 year: 2019 ident: 10.1016/j.envint.2020.106143_b0355 article-title: Global changes in the diurnal cycle of surface ozone publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2018.11.028 – volume: 50 start-page: 79 year: 2016 ident: 10.1016/j.envint.2020.106143_b0040 article-title: Ambient air pollution exposure estimation for the global burden of disease 2013 publication-title: Environ. Sci. Technol. doi: 10.1021/acs.est.5b03709 – volume: 40 start-page: 5304 year: 2006 ident: 10.1016/j.envint.2020.106143_b0210 article-title: Comparison of spatial and temporal variations of aerosol optical thickness and particulate matter over Europe publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2006.04.044 – volume: 115 start-page: 553 year: 2015 ident: 10.1016/j.envint.2020.106143_b0205 article-title: Influence of the choice of gas-phase mechanism on predictions of key gaseous pollutants during the AQMEII phase-2 intercomparison publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2014.11.066 – volume: 28 start-page: 319 year: 2018 ident: 10.1016/j.envint.2020.106143_b0225 article-title: Impacts of fire smoke plumes on regional air quality, 2006–2013 publication-title: J. Exposure Sci. Environ. Epidemiol. doi: 10.1038/s41370-017-0013-x – volume: 5 year: 2010 ident: 10.1016/j.envint.2020.106143_b0215 article-title: Ambient air pollution and the progression of atherosclerosis in adults publication-title: PLoS ONE doi: 10.1371/annotation/21f6b02b-e533-46ca-9356-86a0eef8434e – volume: 2011 year: 2011 ident: 10.1016/j.envint.2020.106143_b0005 article-title: Development of gridded surface meteorological datafor ecological applications and modelling publication-title: Int. J. Climatol. – start-page: 630 year: 2016 ident: 10.1016/j.envint.2020.106143_b0165 article-title: Identity Mappings in Deep Residual Networks – volume: 67 start-page: 768 year: 2005 ident: 10.1016/j.envint.2020.106143_b0465 article-title: Regularization and variable selection via the elastic net (vol B 67, pg 301, 2005) publication-title: J. Roy. Stat. Soc. Ser. B-Stat. Methodology doi: 10.1111/j.1467-9868.2005.00527.x – ident: 10.1016/j.envint.2020.106143_b0135 doi: 10.1007/s11869-020-00826-6 – ident: 10.1016/j.envint.2020.106143_b0415 – volume: 7 year: 2016 ident: 10.1016/j.envint.2020.106143_b0060 article-title: A review on predicting ground PM2.5 concentration using satellite aerosol optical depth publication-title: Atmosphere doi: 10.3390/atmos7100129 – ident: 10.1016/j.envint.2020.106143_b0085 – start-page: 226 year: 1996 ident: 10.1016/j.envint.2020.106143_b0095 article-title: A density-based algorithm for discovering clusters in large spatial databases with noise – volume: 124 start-page: 1334 year: 2016 ident: 10.1016/j.envint.2020.106143_b0340 article-title: Critical review of health impacts of wildfire smoke exposure publication-title: Environ. Health Perspect. doi: 10.1289/ehp.1409277 – volume: 18 start-page: 15921 year: 2018 ident: 10.1016/j.envint.2020.106143_b0360 article-title: Relationships between the planetary boundary layer height and surface pollutants derived from lidar observations over China: regional pattern and influencing factors publication-title: Atmos. Chem. Phys. doi: 10.5194/acp-18-15921-2018 – start-page: 770 year: 2016 ident: 10.1016/j.envint.2020.106143_b0160 article-title: Deep residual learning for image recognition – volume: 120 start-page: 824 year: 2012 ident: 10.1016/j.envint.2020.106143_b0010 article-title: Modeling the residential infiltration of outdoor PM2.5 in the Multi-Ethnic Study of Atherosclerosis and Air Pollution (MESA Air) publication-title: Environ. Health Perspect. doi: 10.1289/ehp.1104447 – volume: 107 start-page: 118 year: 2015 ident: 10.1016/j.envint.2020.106143_b0105 article-title: Artificial neural networks forecasting of PM2.5 pollution using air mass trajectory based geographic model and wavelet transformation publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2015.02.030 – volume: 50 start-page: 6546 year: 2016 ident: 10.1016/j.envint.2020.106143_b0235 article-title: Enhancing the applicability of satellite remote sensing for PM2.5 estimation using MODIS deep blue AOD and land use regression in California, United States publication-title: Environ. Sci. Technol. doi: 10.1021/acs.est.6b01438 – volume: 32 start-page: 2130 year: 2014 ident: 10.1016/j.envint.2020.106143_b0270 article-title: Effect of exposure to PM2.5 on blood pressure: a systematic review and meta-analysis publication-title: J. Hypertens. doi: 10.1097/HJH.0000000000000342 – volume: 541 start-page: 1083 year: 2016 ident: 10.1016/j.envint.2020.106143_b0345 article-title: Fine and ultrafine particulate organic carbon in the Los Angeles basin: trends in sources and composition publication-title: Sci. Total Environ. doi: 10.1016/j.scitotenv.2015.09.133 – volume: 117 start-page: 886 year: 2009 ident: 10.1016/j.envint.2020.106143_b0280 article-title: Estimating regional spatial and temporal variability of PM2.5 concentrations using satellite data, meteorology, and land use information publication-title: Environ. Health Perspect. doi: 10.1289/ehp.0800123 – volume: 125 start-page: 97 year: 2019 ident: 10.1016/j.envint.2020.106143_b0130 article-title: Exposure measurement error in air pollution studies: a framework for assessing shared, multiplicative measurement error in ensemble learning estimates of nitrogen oxides publication-title: Environ. Int. doi: 10.1016/j.envint.2018.12.025 – volume: 111 year: 2006 ident: 10.1016/j.envint.2020.106143_b0390 article-title: Estimating ground-level PM2.5 using aerosol optical depth determined from satellite remote sensing publication-title: J. Geophys. Res.-Atmos. doi: 10.1029/2005JD006996 – volume: 114 start-page: 50 year: 2010 ident: 10.1016/j.envint.2020.106143_b0400 article-title: Satellite-based estimation of regional particulate matter (PM) in Beijing using vertical-and-RH correcting method publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2009.08.009 – volume: 47 start-page: 7233 year: 2013 ident: 10.1016/j.envint.2020.106143_b0025 article-title: A hybrid approach to estimating national scale spatiotemporal variability of PM2.5 in the contiguous United States publication-title: Environ. Sci. Technol. doi: 10.1021/es400039u – year: 2016 ident: 10.1016/j.envint.2020.106143_b0145 – ident: 10.1016/j.envint.2020.106143_b0410 – volume: 151 start-page: 1 year: 2017 ident: 10.1016/j.envint.2020.106143_b0045 article-title: Exposure assessment models for elemental components of particulate matter in an urban environment: a comparison of regression and random forest approaches publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2016.11.066 – ident: 10.1016/j.envint.2020.106143_b0080 – volume: 14 start-page: 6049 year: 2014 ident: 10.1016/j.envint.2020.106143_b0385 article-title: Impact of data quality and surface-to-column representativeness on the PM2.5/satellite AOD relationship for the contiguous United States publication-title: Atmos. Chem. Phys. doi: 10.5194/acp-14-6049-2014 – year: 2009 ident: 10.1016/j.envint.2020.106143_b0240 article-title: Atmospheric aerosol monitoring from satellite observations: a history of three decades – volume: 92 start-page: 1895 year: 2011 ident: 10.1016/j.envint.2020.106143_b0370 article-title: Uncertainty and risk in wildland fire management: a review publication-title: J. Environ. Manage. doi: 10.1016/j.jenvman.2011.03.015 – volume: 198 start-page: 140 year: 2017 ident: 10.1016/j.envint.2020.106143_b0150 article-title: Estimating ground-level PM2.5 concentrations in Beijing using a satellite-based geographically and temporally weighted regression model publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2017.06.001 – volume: 44 start-page: 299 year: 2014 ident: 10.1016/j.envint.2020.106143_b0275 article-title: Toxicological and epidemiological studies of cardiovascular effects of ambient air fine particulate matter (PM2.5) and its chemical components: Coherence and public health implications publication-title: Crit. Rev. Toxicol. doi: 10.3109/10408444.2013.861796 – ident: 10.1016/j.envint.2020.106143_b0420 – volume: 136 start-page: 196 year: 2015 ident: 10.1016/j.envint.2020.106143_b0290 article-title: Systematic review and meta-analysis of the adverse health effects of ambient PM2. 5 and PM10 pollution in the Chinese population publication-title: Environ. Res. doi: 10.1016/j.envres.2014.06.029 – volume: 181 start-page: 145 year: 2018 ident: 10.1016/j.envint.2020.106143_b0450 article-title: An improved geographically weighted regression model for PM2.5 concentration estimation in large areas publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2018.03.017 – volume: 44 start-page: 3976 year: 2010 ident: 10.1016/j.envint.2020.106143_b0365 article-title: Correlations between fine particulate matter (PM2. 5) and meteorological variables in the United States: implications for the sensitivity of PM2. 5 to climate change publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2010.06.060 – volume: 8 start-page: E69 year: 2016 ident: 10.1016/j.envint.2020.106143_b0435 article-title: The impact of PM2.5 on the human respiratory system publication-title: J. Thoracic Disease – volume: 35 start-page: 1 year: 2001 ident: 10.1016/j.envint.2020.106143_b0320 article-title: Exposure assessment of air pollutants: a review on spatial heterogeneity and indoor/outdoor/personal exposure to suspended particulate matter, nitrogen dioxide and ozone publication-title: Atmos. Environ. doi: 10.1016/S1352-2310(00)00330-7 – volume: 41 start-page: 2928 year: 2014 ident: 10.1016/j.envint.2020.106143_b0065 article-title: Large wildfire trends in the western United States, 1984–2011 publication-title: Geophys. Res. Lett. doi: 10.1002/2014GL059576 – volume: 26 start-page: 572 year: 2016 ident: 10.1016/j.envint.2020.106143_b0195 article-title: Fine particulate matter (PM2.5) association with peripheral artery disease admissions in northeastern United States publication-title: Int. J. Environ. Health Res. doi: 10.1080/09603123.2016.1217315 – volume: 8 start-page: 652 year: 2017 ident: 10.1016/j.envint.2020.106143_b0035 article-title: Recursive neural network model for analysis and forecast of PM10 and PM2.5 publication-title: Atmos. Pollut. Res. doi: 10.1016/j.apr.2016.12.014 – volume: 140 start-page: 220 year: 2014 ident: 10.1016/j.envint.2020.106143_b0175 article-title: Estimating ground-level PM2.5 concentrations in the Southeastern United States using MAIAC AOD retrievals and a two-stage model publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2013.08.032 – volume: 14 start-page: 6643 year: 2014 ident: 10.1016/j.envint.2020.106143_b0185 article-title: Global top-down smoke-aerosol emissions estimation using satellite fire radiative power measurements publication-title: Atmos. Chem. Phys. doi: 10.5194/acp-14-6643-2014 – volume: 655 start-page: 1240 year: 2019 ident: 10.1016/j.envint.2020.106143_b0125 article-title: The association between PM2.5 exposure and neurological disorders: a systematic review and meta-analysis publication-title: Sci. Total Environ. doi: 10.1016/j.scitotenv.2018.11.218 – volume: 49 start-page: 8576 year: 2015 ident: 10.1016/j.envint.2020.106143_b0190 article-title: Using high-resolution satellite aerosol optical depth to estimate daily PM2. 5 geographical distribution in Mexico City publication-title: Environ. Sci. Technol. doi: 10.1021/acs.est.5b00859 – volume: 49 start-page: 12280 year: 2015 ident: 10.1016/j.envint.2020.106143_b0430 article-title: Daily estimation of ground-level PM2.5 concentrations over Beijing using 3 km resolution MODIS AOD publication-title: Environ. Sci. Technol. doi: 10.1021/acs.est.5b01413 – volume: 14 start-page: 2015 year: 2014 ident: 10.1016/j.envint.2020.106143_b0285 article-title: Comparison of MODIS 3 km and 10 km resolution aerosol optical depth retrievals over land with airborne sunphotometer measurements during ARCTAS summer 2008 publication-title: Atmos. Chem. Phys. doi: 10.5194/acp-14-2015-2014 – volume: 146 start-page: 108 year: 2018 ident: 10.1016/j.envint.2020.106143_b0440 article-title: A new generation of the United States National Land Cover Database: Requirements, research priorities, design, and implementation strategies publication-title: ISPRS J. Photogramm. Remote Sens. doi: 10.1016/j.isprsjprs.2018.09.006 – volume: 26 start-page: 13963 year: 2019 ident: 10.1016/j.envint.2020.106143_b0445 article-title: Maternal fine particulate matter (PM2.5) exposure and adverse birth outcomes: an updated systematic review based on cohort studies publication-title: Environ. Sci. Pollut. Res. doi: 10.1007/s11356-019-04644-x – volume: 30 start-page: 6823 year: 2017 ident: 10.1016/j.envint.2020.106143_b0335 article-title: The MERRA-2 aerosol reanalysis, 1980 onward. Part I: System description and data assimilation evaluation publication-title: J. Clim. doi: 10.1175/JCLI-D-16-0609.1 – volume: 45 start-page: 6267 year: 2011 ident: 10.1016/j.envint.2020.106143_b0200 article-title: Assessing temporally and spatially resolved PM2.5 exposures for epidemiological studies using satellite aerosol optical depth measurements publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2011.08.066 – volume: 26 start-page: 377 year: 2015 ident: 10.1016/j.envint.2020.106143_b0245 article-title: Spatiotemporal prediction of fine particulate matter using high-resolution satellite images in the southeastern U.S. 2003–2011 publication-title: J. Expo. Sci. Environ. Epidemiol. doi: 10.1038/jes.2015.41 – volume: 217 start-page: 573 year: 2018 ident: 10.1016/j.envint.2020.106143_b0260 article-title: Estimation of PM2. 5 concentrations at a high spatiotemporal resolution using constrained mixed-effect bagging models with MAIAC aerosol optical depth publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2018.09.001 – volume: 50 start-page: 4752 year: 2016 ident: 10.1016/j.envint.2020.106143_b0300 article-title: Improving the accuracy of daily PM2.5 distributions derived from the fusion of ground-level measurements with aerosol optical depth observations, a case study in north China publication-title: Environ. Sci. Technol. doi: 10.1021/acs.est.5b05940 – volume: 242 start-page: 675 year: 2018 ident: 10.1016/j.envint.2020.106143_b0180 article-title: Predicting monthly high-resolution PM2.5 concentrations with random forest model in the North China Plain publication-title: Environ. Pollut. doi: 10.1016/j.envpol.2018.07.016 – ident: 10.1016/j.envint.2020.106143_b0295 – volume: 12 year: 2019 ident: 10.1016/j.envint.2020.106143_b0455 article-title: Gestational exposure to particulate matter 2.5 (PM2.5) leads to spatial memory dysfunction and neurodevelopmental impairment in hippocampus of mice offspring publication-title: Front. Neurosci. doi: 10.3389/fnins.2018.01000 – volume: 130 year: 2019 ident: 10.1016/j.envint.2020.106143_b0070 article-title: An ensemble-based model of PM2.5 concentration across the contiguous United States with high spatiotemporal resolution publication-title: Environ. Int. doi: 10.1016/j.envint.2019.104909 – ident: 10.1016/j.envint.2020.106143_b0220 – volume: 96 start-page: 2059 year: 2015 ident: 10.1016/j.envint.2020.106143_b0350 article-title: Noaa's hysplit atmospheric transport and dispersion modeling system publication-title: Bull. Am. Meteorol. Soc. doi: 10.1175/BAMS-D-14-00110.1 – volume: 8 start-page: 262 year: 2016 ident: 10.1016/j.envint.2020.106143_b0020 article-title: A geographically and temporallyweighted regression model for ground-level PM2.5 estimation from satellite-derived 500 m resolution AOD publication-title: Remote Sens. doi: 10.3390/rs8030262 – volume: 102 start-page: 260 year: 2015 ident: 10.1016/j.envint.2020.106143_b0250 article-title: How well do satellite AOD observations represent the spatial and temporal variability of PM2.5 concentration for the United States? publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2014.12.010 – volume: 12 start-page: 3303 year: 2019 ident: 10.1016/j.envint.2020.106143_b0395 article-title: Relationship analysis of PM 2.5 and boundary layer height using an aerosol and turbulence detection lidar publication-title: Atmos. Meas. Tech. doi: 10.5194/amt-12-3303-2019 – year: 2007 ident: 10.1016/j.envint.2020.106143_b0110 – year: 2018 ident: 10.1016/j.envint.2020.106143_b0090 – volume: 14 start-page: 10013 year: 2014 ident: 10.1016/j.envint.2020.106143_b0100 article-title: Modeling regional aerosol and aerosol precursor variability over California and its sensitivity to emissions and long-range transport during the 2010 CalNex and CARES campaigns publication-title: Atmos. Chem. Phys. doi: 10.5194/acp-14-10013-2014 – volume: 51 start-page: 6936 year: 2017 ident: 10.1016/j.envint.2020.106143_b0170 article-title: Estimating PM2.5 concentrations in the conterminous United States using the random forest approach publication-title: Environ. Sci. Technol. doi: 10.1021/acs.est.7b01210 – volume: 53 start-page: 12774 year: 2019 ident: 10.1016/j.envint.2020.106143_b0230 article-title: Benefits of high resolution PM2.5 prediction using satellite MAIAC AOD and land use regression for exposure assessment: California examples publication-title: Environ. Sci. Technol. doi: 10.1021/acs.est.9b03799 – volume: 69 start-page: 660 year: 2014 ident: 10.1016/j.envint.2020.106143_b0015 article-title: Epidemiological time series studies of PM2. 5 and daily mortality and hospital admissions: a systematic review and meta-analysis publication-title: Thorax doi: 10.1136/thoraxjnl-2013-204492 – volume: 231 year: 2019 ident: 10.1016/j.envint.2020.106143_b0405 article-title: Estimating 1-km-resolution PM2.5 concentrations across China using the space-time random forest approach publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2019.111221 – volume: 10 year: 2017 ident: 10.1016/j.envint.2020.106143_b0055 article-title: Ten quick tips for machine learning in computational biology publication-title: Biodata Min. doi: 10.1186/s13040-017-0155-3 – volume: 34 start-page: 88 year: 2001 ident: 10.1016/j.envint.2020.106143_b0380 article-title: East versus West in the US: chemical characteristics of PM2.5 during the winter of 1999 publication-title: Aerosol Sci. Technol. doi: 10.1080/02786820118957 – volume: 40 start-page: 5880 year: 2006 ident: 10.1016/j.envint.2020.106143_b0155 article-title: Satellite remote sensing of particulate matter and air quality assessment over global cities publication-title: Atmos. Environ. doi: 10.1016/j.atmosenv.2006.03.016 – volume: 4 year: 2010 ident: 10.1016/j.envint.2020.106143_b0375 article-title: Neocortical layer 6, a review publication-title: Front. Neuroanat. – volume: 50 start-page: 4712 year: 2016 ident: 10.1016/j.envint.2020.106143_b0075 article-title: Assessing PM2.5 exposures with high spatiotemporal resolution across the continental United States publication-title: Environ Sci Technol doi: 10.1021/acs.est.5b06121 – start-page: 1189 year: 2001 ident: 10.1016/j.envint.2020.106143_b0115 article-title: Greedy function approximation: a gradient boosting machine publication-title: Ann. Stat. – volume: 11 start-page: 5741 year: 2018 ident: 10.1016/j.envint.2020.106143_b0315 article-title: MODIS collection 6 MAIAC algorithm publication-title: Atmos. Meas. Tech. doi: 10.5194/amt-11-5741-2018 – volume: 24 start-page: 44 year: 2015 ident: 10.1016/j.envint.2020.106143_b0140 article-title: Peeking inside the black box: Visualizing statistical learning with plots of individual conditional expectation publication-title: J. Comput. Graphical Stat. doi: 10.1080/10618600.2014.907095 – ident: 10.1016/j.envint.2020.106143_b0330 – volume: 14 start-page: 1171 year: 1986 ident: 10.1016/j.envint.2020.106143_b0050 article-title: The use of subseries values for estimating the variance of a general statistic from a stationary sequence publication-title: Ann. Statist. doi: 10.1214/aos/1176350057 – volume: 128 start-page: 310 year: 2019 ident: 10.1016/j.envint.2020.106143_b0265 article-title: Cluster-based bagging of constrained mixed-effects models for high spatiotemporal resolution nitrogen oxides prediction over large regions publication-title: Environ. Int. doi: 10.1016/j.envint.2019.04.057 – ident: 10.1016/j.envint.2020.106143_b0030 – volume: 199 start-page: 437 year: 2017 ident: 10.1016/j.envint.2020.106143_b0425 article-title: Full-coverage high-resolution daily PM2.5 estimation using MAIAC AOD in the Yangtze River Delta of China publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2017.07.023 – volume: 237 year: 2020 ident: 10.1016/j.envint.2020.106143_b0255 article-title: Spatiotemporal imputation of MAIAC AOD using deep learning with downscaling publication-title: Remote Sens. Environ. doi: 10.1016/j.rse.2019.111584 – volume: 22 start-page: 3383 year: 2015 ident: 10.1016/j.envint.2020.106143_b0460 article-title: Maternal exposure to fine particulate matter (PM2.5) and pregnancy outcomes: a meta-analysis publication-title: Environ. Sci. Pollut. Res. doi: 10.1007/s11356-014-3458-7 – volume: 116 year: 2011 ident: 10.1016/j.envint.2020.106143_b0310 article-title: Multiangle implementation of atmospheric correction (MAIAC): 2. Aerosol algorithm publication-title: J. Geophys. Res.-Atmos. |
| SSID | ssj0002485 |
| Score | 2.57762 |
| Snippet | •California has high variability in PM2.5 sources, meteorology and topography.•We used ensemble deep learning with multisource big data to improve PM2.5... Estimating PM2.5 concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies.... Estimating PM₂.₅ concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health effect studies.... Introduction: Estimating PM2.5 concentrations and their prediction uncertainties at a high spatiotemporal resolution is important for air pollution health... |
| SourceID | doaj pubmedcentral proquest crossref nasa elsevier |
| SourceType | Open Website Open Access Repository Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 106143 |
| SubjectTerms | aerosols air pollution Air pollution exposure air temperature California carbon monoxide cloud cover Computer Programming And Software dust Earth Resources And Remote Sensing environment Environment Pollution Geosciences (General) High spatiotemporal resolution land cover Machine learning meteorology PM2.5 prediction relative humidity Remote sensing smoke snowpack spatial distribution topography traffic uncertainty Wildfires |
| Title | Ensemble-based deep learning for estimating PM2.5 over California with multisource big data including wildfire smoke |
| URI | https://dx.doi.org/10.1016/j.envint.2020.106143 https://ntrs.nasa.gov/citations/20205008643 https://www.proquest.com/docview/2446994248 https://www.proquest.com/docview/2552011859 https://pubmed.ncbi.nlm.nih.gov/PMC7643812 https://doaj.org/article/10b913da1bb64b33ac9ad378ab75942c |
| Volume | 145 |
| WOSCitedRecordID | wos000580632000058&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 1873-6750 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002485 issn: 0160-4120 databaseCode: DOA dateStart: 20190101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVESC databaseName: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1873-6750 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002485 issn: 0160-4120 databaseCode: AIEXJ dateStart: 20181201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Rb9MwELZg8ABCCMomOqAyEq9BiZM48eNAnQDBtAeQ-mbZZ2d0dOm0tPz-3dnJ1rzQFx7rXpPad-f7Lrn7zNgHJ33WpFAlCnfCpPDo6bUFkwBFG7Cp8hA0_b06O6sXC3W-c9QX1YRFeuC4cOjVVmW5M5m1srB5bkAZl1e1sVWpCgG0-yLqGZKpfg8moq7I6p0mRSbSoWkuVHZRC1lLdZSChmTo2NkJSoG7fxSbDlrTmREEHRdQ7kSk0xfseQ8l-Umcwkv2wLcT9nSHYHDCjub3fWwo2jtyN2HP4uM6HruQXrHNvO38lV35hMKa4877a96fKHHBEdhyYuMgdIsfz3-IjyWn2k9-39rF6YkuD_WJ8YUAt8sLTgWofNnCaksxEmVWrsFNlndX6z_-kP06nf_8_CXpD2RIAIHRJjEy86V1HiGfBFNBnpoa8Qgx5guT14URrkA4AcpLWSqMj1CKokFMiBtJg3lZfoRLuW79a8Zt3UCjwKBqU0RkDV61ykA0EjCjc7mcsnzQiIaerZwOzVjpoSztUkc9atKjjnqcsuTuV9eRrWOP_CdS9p0scW2HAbRA3Vug3meBU1YNpqJ72BLhCF5quef2h2RZGmfWhfGSMkwafz-YmkZvp1c4pvXrLQph9q7wpkX9D5myJFRXlwr_2chOR_Mcf9Mufwdu8UoS55s4_h8L84Y9oUnF4p-37GBzs_Xv2GP4i4Z4M2MPq0U9Y49Ovs4X32bBfW8BIzpHcg |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Ensemble-based+deep+learning+for+estimating+PM2.5+over+California+with+multisource+big+data+including+wildfire+smoke&rft.jtitle=Environment+international&rft.au=Li%2C+Lianfa&rft.au=Girguis%2C+Mariam&rft.au=Lurmann%2C+Frederick&rft.au=Pavlovic%2C+Nathan&rft.date=2020-12-01&rft.issn=1873-6750&rft.eissn=1873-6750&rft.volume=145&rft.spage=106143&rft_id=info:doi/10.1016%2Fj.envint.2020.106143&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0160-4120&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0160-4120&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0160-4120&client=summon |